Wan-AI

23 models • 16 total models in database

Sort by:

Wan2.2-T2V-A14B-Diffusers

--- license: apache-2.0 pipeline_tag: text-to-video ---

NaNK

license:apache-2.0

207,535

Wan2.1-T2V-14B

💜 Wan &nbsp&nbsp ｜ &nbsp&nbsp 🖥️ GitHub &nbsp&nbsp | &nbsp&nbsp🤗 Hugging Face &nbsp&nbsp | &nbsp&nbsp🤖 ModelScope &nbsp&nbsp | &nbsp&nbsp 📑 Paper (Coming soon) &nbsp&nbsp | &nbsp&nbsp 📑 Blog &nbsp&nbsp | &nbsp&nbsp💬 WeChat Group &nbsp&nbsp | &nbsp&nbsp 📖 Discord &nbsp&nbsp Wan: Open and Advanced Large-Scale Video Generative Models In this repository, we present Wan2.1, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation. Wan2.1 offers these key features: - 👍 SOTA Performance: Wan2.1 consistently outperforms existing open-source models and state-of-the-art commercial solutions across multiple benchmarks. - 👍 Supports Consumer-grade GPUs: The T2V-1.3B model requires only 8.19 GB VRAM, making it compatible with almost all consumer-grade GPUs. It can generate a 5-second 480P video on an RTX 4090 in about 4 minutes (without optimization techniques like quantization). Its performance is even comparable to some closed-source models. - 👍 Multiple Tasks: Wan2.1 excels in Text-to-Video, Image-to-Video, Video Editing, Text-to-Image, and Video-to-Audio, advancing the field of video generation. - 👍 Visual Text Generation: Wan2.1 is the first video model capable of generating both Chinese and English text, featuring robust text generation that enhances its practical applications. - 👍 Powerful Video VAE: Wan-VAE delivers exceptional efficiency and performance, encoding and decoding 1080P videos of any length while preserving temporal information, making it an ideal foundation for video and image generation. This repository features our T2V-14B model, which establishes a new SOTA performance benchmark among both open-source and closed-source models. It demonstrates exceptional capabilities in generating high-quality visuals with significant motion dynamics. It is also the only video model capable of producing both Chinese and English text and supports video generation at both 480P and 720P resolutions. Feb 22, 2025: 👋 We've released the inference code and weights of Wan2.1. 📑 Todo List - Wan2.1 Text-to-Video - [x] Multi-GPU Inference code of the 14B and 1.3B models - [x] Checkpoints of the 14B and 1.3B models - [x] Gradio demo - [ ] Diffusers integration - [ ] ComfyUI integration - Wan2.1 Image-to-Video - [x] Multi-GPU Inference code of the 14B model - [x] Checkpoints of the 14B model - [x] Gradio demo - [ ] Diffusers integration - [ ] ComfyUI integration | Models | Download Link | Notes | | --------------|-------------------------------------------------------------------------------|-------------------------------| | T2V-14B | 🤗 Huggingface 🤖 ModelScope | Supports both 480P and 720P | I2V-14B-720P | 🤗 Huggingface 🤖 ModelScope | Supports 720P | I2V-14B-480P | 🤗 Huggingface 🤖 ModelScope | Supports 480P | T2V-1.3B | 🤗 Huggingface 🤖 ModelScope | Supports 480P > 💡Note: The 1.3B model is capable of generating videos at 720P resolution. However, due to limited training at this resolution, the results are generally less stable compared to 480P. For optimal performance, we recommend using 480P resolution. This repository supports two Text-to-Video models (1.3B and 14B) and two resolutions (480P and 720P). The parameters and configurations for these models are as follows: To facilitate implementation, we will start with a basic version of the inference process that skips the prompt extension step. If you encounter OOM (Out-of-Memory) issues, you can use the `--offloadmodel True` and `--t5cpu` options to reduce GPU memory usage. For example, on an RTX 4090 GPU: > 💡Note: If you are using the `T2V-1.3B` model, we recommend setting the parameter `--sampleguidescale 6`. The `--sampleshift parameter` can be adjusted within the range of 8 to 12 based on the performance. Extending the prompts can effectively enrich the details in the generated videos, further enhancing the video quality. Therefore, we recommend enabling prompt extension. We provide the following two methods for prompt extension: - Use the Dashscope API for extension. - Apply for a `dashscope.apikey` in advance (EN | CN). - Configure the environment variable `DASHAPIKEY` to specify the Dashscope API key. For users of Alibaba Cloud's international site, you also need to set the environment variable `DASHAPIURL` to 'https://dashscope-intl.aliyuncs.com/api/v1'. For more detailed instructions, please refer to the dashscope document. - Use the `qwen-plus` model for text-to-video tasks and `qwen-vl-max` for image-to-video tasks. - You can modify the model used for extension with the parameter `--promptextendmodel`. For example: - By default, the Qwen model on HuggingFace is used for this extension. Users can choose based on the available GPU memory size. - For text-to-video tasks, you can use models like `Qwen/Qwen2.5-14B-Instruct`, `Qwen/Qwen2.5-7B-Instruct` and `Qwen/Qwen2.5-3B-Instruct` - For image-to-video tasks, you can use models like `Qwen/Qwen2.5-VL-7B-Instruct` and `Qwen/Qwen2.5-VL-3B-Instruct`. - Larger models generally provide better extension results but require more GPU memory. - You can modify the model used for extension with the parameter `--promptextendmodel` , allowing you to specify either a local model path or a Hugging Face model. For example: Through manual evaluation, the results generated after prompt extension are superior to those from both closed-source and open-source models. We test the computational efficiency of different Wan2.1 models on different GPUs in the following table. The results are presented in the format: Total time (s) / peak GPU memory (GB). > The parameter settings for the tests presented in this table are as follows: > (1) For the 1.3B model on 8 GPUs, set `--ringsize 8` and `--ulyssessize 1`; > (2) For the 14B model on 1 GPU, use `--offloadmodel True`; > (3) For the 1.3B model on a single 4090 GPU, set `--offloadmodel True --t5cpu`; > (4) For all testings, no prompt extension was applied, meaning `--usepromptextend` was not enabled. Community Contributions - DiffSynth-Studio provides more support for Wan, including video-to-video, FP8 quantization, VRAM optimization, LoRA training, and more. Please refer to their examples. Wan2.1 is designed on the mainstream diffusion transformer paradigm, achieving significant advancements in generative capabilities through a series of innovations. These include our novel spatio-temporal variational autoencoder (VAE), scalable training strategies, large-scale data construction, and automated evaluation metrics. Collectively, these contributions enhance the model’s performance and versatility. (1) 3D Variational Autoencoders We propose a novel 3D causal VAE architecture, termed Wan-VAE specifically designed for video generation. By combining multiple strategies, we improve spatio-temporal compression, reduce memory usage, and ensure temporal causality. Wan-VAE demonstrates significant advantages in performance efficiency compared to other open-source VAEs. Furthermore, our Wan-VAE can encode and decode unlimited-length 1080P videos without losing historical temporal information, making it particularly well-suited for video generation tasks. Wan2.1 is designed using the Flow Matching framework within the paradigm of mainstream Diffusion Transformers. Our model's architecture uses the T5 Encoder to encode multilingual text input, with cross-attention in each transformer block embedding the text into the model structure. Additionally, we employ an MLP with a Linear layer and a SiLU layer to process the input time embeddings and predict six modulation parameters individually. This MLP is shared across all transformer blocks, with each block learning a distinct set of biases. Our experimental findings reveal a significant performance improvement with this approach at the same parameter scale. | Model | Dimension | Input Dimension | Output Dimension | Feedforward Dimension | Frequency Dimension | Number of Heads | Number of Layers | |--------|-----------|-----------------|------------------|-----------------------|---------------------|-----------------|------------------| | 1.3B | 1536 | 16 | 16 | 8960 | 256 | 12 | 30 | | 14B | 5120 | 16 | 16 | 13824 | 256 | 40 | 40 | We curated and deduplicated a candidate dataset comprising a vast amount of image and video data. During the data curation process, we designed a four-step data cleaning process, focusing on fundamental dimensions, visual quality and motion quality. Through the robust data processing pipeline, we can easily obtain high-quality, diverse, and large-scale training sets of images and videos. Comparisons to SOTA We compared Wan2.1 with leading open-source and closed-source models to evaluate the performace. Using our carefully designed set of 1,035 internal prompts, we tested across 14 major dimensions and 26 sub-dimensions. We then compute the total score by performing a weighted calculation on the scores of each dimension, utilizing weights derived from human preferences in the matching process. The detailed results are shown in the table below. These results demonstrate our model's superior performance compared to both open-source and closed-source models. Citation If you find our work helpful, please cite us. License Agreement The models in this repository are licensed under the Apache 2.0 License. We claim no rights over the your generate contents, granting you the freedom to use them while ensuring that your usage complies with the provisions of this license. You are fully accountable for your use of the models, which must not involve sharing any content that violates applicable laws, causes harm to individuals or groups, disseminates personal information intended for harm, spreads misinformation, or targets vulnerable populations. For a complete list of restrictions and details regarding your rights, please refer to the full text of the license. We would like to thank the contributors to the SD3, Qwen, umt5-xxl, diffusers and HuggingFace repositories, for their open research. Contact Us If you would like to leave a message to our research or product teams, feel free to join our Discord or WeChat groups!

Wan2.1-T2V-14B-Diffusers

NaNK

license:apache-2.0

14,242

Wan2.1-I2V-14B-720P

Wan2.1-T2V-1.3B

💜 Wan &nbsp&nbsp ｜ &nbsp&nbsp 🖥️ GitHub &nbsp&nbsp | &nbsp&nbsp🤗 Hugging Face &nbsp&nbsp | &nbsp&nbsp🤖 ModelScope &nbsp&nbsp | &nbsp&nbsp 📑 Paper (Coming soon) &nbsp&nbsp | &nbsp&nbsp 📑 Blog &nbsp&nbsp | &nbsp&nbsp💬 WeChat Group &nbsp&nbsp | &nbsp&nbsp 📖 Discord &nbsp&nbsp Wan: Open and Advanced Large-Scale Video Generative Models In this repository, we present Wan2.1, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation. Wan2.1 offers these key features: - 👍 SOTA Performance: Wan2.1 consistently outperforms existing open-source models and state-of-the-art commercial solutions across multiple benchmarks. - 👍 Supports Consumer-grade GPUs: The T2V-1.3B model requires only 8.19 GB VRAM, making it compatible with almost all consumer-grade GPUs. It can generate a 5-second 480P video on an RTX 4090 in about 4 minutes (without optimization techniques like quantization). Its performance is even comparable to some closed-source models. - 👍 Multiple Tasks: Wan2.1 excels in Text-to-Video, Image-to-Video, Video Editing, Text-to-Image, and Video-to-Audio, advancing the field of video generation. - 👍 Visual Text Generation: Wan2.1 is the first video model capable of generating both Chinese and English text, featuring robust text generation that enhances its practical applications. - 👍 Powerful Video VAE: Wan-VAE delivers exceptional efficiency and performance, encoding and decoding 1080P videos of any length while preserving temporal information, making it an ideal foundation for video and image generation. This repository hosts our T2V-1.3B model, a versatile solution for video generation that is compatible with nearly all consumer-grade GPUs. In this way, we hope that Wan2.1 can serve as an easy-to-use tool for more creative teams in video creation, providing a high-quality foundational model for academic teams with limited computing resources. This will facilitate both the rapid development of the video creation community and the swift advancement of video technology. Feb 25, 2025: 👋 We've released the inference code and weights of Wan2.1. 📑 Todo List - Wan2.1 Text-to-Video - [x] Multi-GPU Inference code of the 14B and 1.3B models - [x] Checkpoints of the 14B and 1.3B models - [x] Gradio demo - [ ] Diffusers integration - [ ] ComfyUI integration - Wan2.1 Image-to-Video - [x] Multi-GPU Inference code of the 14B model - [x] Checkpoints of the 14B model - [x] Gradio demo - [ ] Diffusers integration - [ ] ComfyUI integration | Models | Download Link | Notes | | --------------|-------------------------------------------------------------------------------|-------------------------------| | T2V-14B | 🤗 Huggingface 🤖 ModelScope | Supports both 480P and 720P | I2V-14B-720P | 🤗 Huggingface 🤖 ModelScope | Supports 720P | I2V-14B-480P | 🤗 Huggingface 🤖 ModelScope | Supports 480P | T2V-1.3B | 🤗 Huggingface 🤖 ModelScope | Supports 480P > 💡Note: The 1.3B model is capable of generating videos at 720P resolution. However, due to limited training at this resolution, the results are generally less stable compared to 480P. For optimal performance, we recommend using 480P resolution. This repository supports two Text-to-Video models (1.3B and 14B) and two resolutions (480P and 720P). The parameters and configurations for these models are as follows: To facilitate implementation, we will start with a basic version of the inference process that skips the prompt extension step. If you encounter OOM (Out-of-Memory) issues, you can use the `--offloadmodel True` and `--t5cpu` options to reduce GPU memory usage. For example, on an RTX 4090 GPU: > 💡Note: If you are using the `T2V-1.3B` model, we recommend setting the parameter `--sampleguidescale 6`. The `--sampleshift parameter` can be adjusted within the range of 8 to 12 based on the performance. Extending the prompts can effectively enrich the details in the generated videos, further enhancing the video quality. Therefore, we recommend enabling prompt extension. We provide the following two methods for prompt extension: - Use the Dashscope API for extension. - Apply for a `dashscope.apikey` in advance (EN | CN). - Configure the environment variable `DASHAPIKEY` to specify the Dashscope API key. For users of Alibaba Cloud's international site, you also need to set the environment variable `DASHAPIURL` to 'https://dashscope-intl.aliyuncs.com/api/v1'. For more detailed instructions, please refer to the dashscope document. - Use the `qwen-plus` model for text-to-video tasks and `qwen-vl-max` for image-to-video tasks. - You can modify the model used for extension with the parameter `--promptextendmodel`. For example: - By default, the Qwen model on HuggingFace is used for this extension. Users can choose based on the available GPU memory size. - For text-to-video tasks, you can use models like `Qwen/Qwen2.5-14B-Instruct`, `Qwen/Qwen2.5-7B-Instruct` and `Qwen/Qwen2.5-3B-Instruct` - For image-to-video tasks, you can use models like `Qwen/Qwen2.5-VL-7B-Instruct` and `Qwen/Qwen2.5-VL-3B-Instruct`. - Larger models generally provide better extension results but require more GPU memory. - You can modify the model used for extension with the parameter `--promptextendmodel` , allowing you to specify either a local model path or a Hugging Face model. For example: We employ our Wan-Bench framework to evaluate the performance of the T2V-1.3B model, with the results displayed in the table below. The results indicate that our smaller 1.3B model surpasses the overall metrics of larger open-source models, demonstrating the effectiveness of WanX2.1's architecture and the data construction pipeline. We test the computational efficiency of different Wan2.1 models on different GPUs in the following table. The results are presented in the format: Total time (s) / peak GPU memory (GB). > The parameter settings for the tests presented in this table are as follows: > (1) For the 1.3B model on 8 GPUs, set `--ringsize 8` and `--ulyssessize 1`; > (2) For the 14B model on 1 GPU, use `--offloadmodel True`; > (3) For the 1.3B model on a single 4090 GPU, set `--offloadmodel True --t5cpu`; > (4) For all testings, no prompt extension was applied, meaning `--usepromptextend` was not enabled. Wan2.1 is designed on the mainstream diffusion transformer paradigm, achieving significant advancements in generative capabilities through a series of innovations. These include our novel spatio-temporal variational autoencoder (VAE), scalable training strategies, large-scale data construction, and automated evaluation metrics. Collectively, these contributions enhance the model’s performance and versatility. (1) 3D Variational Autoencoders We propose a novel 3D causal VAE architecture, termed Wan-VAE specifically designed for video generation. By combining multiple strategies, we improve spatio-temporal compression, reduce memory usage, and ensure temporal causality. Wan-VAE demonstrates significant advantages in performance efficiency compared to other open-source VAEs. Furthermore, our Wan-VAE can encode and decode unlimited-length 1080P videos without losing historical temporal information, making it particularly well-suited for video generation tasks. Wan2.1 is designed using the Flow Matching framework within the paradigm of mainstream Diffusion Transformers. Our model's architecture uses the T5 Encoder to encode multilingual text input, with cross-attention in each transformer block embedding the text into the model structure. Additionally, we employ an MLP with a Linear layer and a SiLU layer to process the input time embeddings and predict six modulation parameters individually. This MLP is shared across all transformer blocks, with each block learning a distinct set of biases. Our experimental findings reveal a significant performance improvement with this approach at the same parameter scale. | Model | Dimension | Input Dimension | Output Dimension | Feedforward Dimension | Frequency Dimension | Number of Heads | Number of Layers | |--------|-----------|-----------------|------------------|-----------------------|---------------------|-----------------|------------------| | 1.3B | 1536 | 16 | 16 | 8960 | 256 | 12 | 30 | | 14B | 5120 | 16 | 16 | 13824 | 256 | 40 | 40 | We curated and deduplicated a candidate dataset comprising a vast amount of image and video data. During the data curation process, we designed a four-step data cleaning process, focusing on fundamental dimensions, visual quality and motion quality. Through the robust data processing pipeline, we can easily obtain high-quality, diverse, and large-scale training sets of images and videos. Comparisons to SOTA We compared Wan2.1 with leading open-source and closed-source models to evaluate the performace. Using our carefully designed set of 1,035 internal prompts, we tested across 14 major dimensions and 26 sub-dimensions. Then we calculated the total score through a weighted average based on the importance of each dimension. The detailed results are shown in the table below. These results demonstrate our model's superior performance compared to both open-source and closed-source models. Citation If you find our work helpful, please cite us. License Agreement The models in this repository are licensed under the Apache 2.0 License. We claim no rights over the your generate contents, granting you the freedom to use them while ensuring that your usage complies with the provisions of this license. You are fully accountable for your use of the models, which must not involve sharing any content that violates applicable laws, causes harm to individuals or groups, disseminates personal information intended for harm, spreads misinformation, or targets vulnerable populations. For a complete list of restrictions and details regarding your rights, please refer to the full text of the license. We would like to thank the contributors to the SD3, Qwen, umt5-xxl, diffusers and HuggingFace repositories, for their open research. Contact Us If you would like to leave a message to our research or product teams, feel free to join our Discord or WeChat groups!

Wan2.1-VACE-14B

💜 Wan &nbsp&nbsp ｜ &nbsp&nbsp 🖥️ GitHub &nbsp&nbsp | &nbsp&nbsp🤗 Hugging Face &nbsp&nbsp | &nbsp&nbsp🤖 ModelScope &nbsp&nbsp | &nbsp&nbsp 📑 Technical Report &nbsp&nbsp | &nbsp&nbsp 📑 Blog &nbsp&nbsp | &nbsp&nbsp💬 WeChat Group &nbsp&nbsp | &nbsp&nbsp 📖 Discord &nbsp&nbsp Wan: Open and Advanced Large-Scale Video Generative Models In this repository, we present Wan2.1, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation. Wan2.1 offers these key features: - 👍 SOTA Performance: Wan2.1 consistently outperforms existing open-source models and state-of-the-art commercial solutions across multiple benchmarks. - 👍 Supports Consumer-grade GPUs: The T2V-1.3B model requires only 8.19 GB VRAM, making it compatible with almost all consumer-grade GPUs. It can generate a 5-second 480P video on an RTX 4090 in about 4 minutes (without optimization techniques like quantization). Its performance is even comparable to some closed-source models. - 👍 Multiple Tasks: Wan2.1 excels in Text-to-Video, Image-to-Video, Video Editing, Text-to-Image, and Video-to-Audio, advancing the field of video generation. - 👍 Visual Text Generation: Wan2.1 is the first video model capable of generating both Chinese and English text, featuring robust text generation that enhances its practical applications. - 👍 Powerful Video VAE: Wan-VAE delivers exceptional efficiency and performance, encoding and decoding 1080P videos of any length while preserving temporal information, making it an ideal foundation for video and image generation. May 14, 2025: 👋 We introduce Wan2.1 VACE, an all-in-one model for video creation and editing, along with its inference code, weights, and technical report! Apr 17, 2025: 👋 We introduce Wan2.1 FLF2V with its inference code and weights! Mar 21, 2025: 👋 We are excited to announce the release of the Wan2.1 technical report. We welcome discussions and feedback! Mar 3, 2025: 👋 Wan2.1's T2V and I2V have been integrated into Diffusers (T2V | I2V). Feel free to give it a try! Feb 27, 2025: 👋 Wan2.1 has been integrated into ComfyUI. Enjoy! Feb 25, 2025: 👋 We've released the inference code and weights of Wan2.1. Community Works If your work has improved Wan2.1 and you would like more people to see it, please inform us. - Phantom has developed a unified video generation framework for single and multi-subject references based on Wan2.1-T2V-1.3B. Please refer to their examples. - UniAnimate-DiT, based on Wan2.1-14B-I2V, has trained a Human image animation model and has open-sourced the inference and training code. Feel free to enjoy it! - CFG-Zero enhances Wan2.1 (covering both T2V and I2V models) from the perspective of CFG. - TeaCache now supports Wan2.1 acceleration, capable of increasing speed by approximately 2x. Feel free to give it a try! - DiffSynth-Studio provides more support for Wan2.1, including video-to-video, FP8 quantization, VRAM optimization, LoRA training, and more. Please refer to their examples. 📑 Todo List - Wan2.1 Text-to-Video - [x] Multi-GPU Inference code of the 14B and 1.3B models - [x] Checkpoints of the 14B and 1.3B models - [x] Gradio demo - [x] ComfyUI integration - [x] Diffusers integration - [ ] Diffusers + Multi-GPU Inference - Wan2.1 Image-to-Video - [x] Multi-GPU Inference code of the 14B model - [x] Checkpoints of the 14B model - [x] Gradio demo - [x] ComfyUI integration - [x] Diffusers integration - [ ] Diffusers + Multi-GPU Inference - Wan2.1 First-Last-Frame-to-Video - [x] Multi-GPU Inference code of the 14B model - [x] Checkpoints of the 14B model - [x] Gradio demo - [ ] ComfyUI integration - [ ] Diffusers integration - [ ] Diffusers + Multi-GPU Inference - Wan2.1 VACE - [x] Multi-GPU Inference code of the 14B and 1.3B models - [x] Checkpoints of the 14B and 1.3B models - [x] Gradio demo - [x] ComfyUI integration - [ ] Diffusers integration - [ ] Diffusers + Multi-GPU Inference | Models | Download Link | Notes | |--------------|---------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------| | T2V-14B | 🤗 Huggingface 🤖 ModelScope | Supports both 480P and 720P | I2V-14B-720P | 🤗 Huggingface 🤖 ModelScope | Supports 720P | I2V-14B-480P | 🤗 Huggingface 🤖 ModelScope | Supports 480P | T2V-1.3B | 🤗 Huggingface 🤖 ModelScope | Supports 480P | FLF2V-14B | 🤗 Huggingface 🤖 ModelScope | Supports 720P | VACE-1.3B | 🤗 Huggingface 🤖 ModelScope | Supports 480P | VACE-14B | 🤗 Huggingface 🤖 ModelScope | Supports both 480P and 720P > 💡Note: > The 1.3B model is capable of generating videos at 720P resolution. However, due to limited training at this resolution, the results are generally less stable compared to 480P. For optimal performance, we recommend using 480P resolution. > For the first-last frame to video generation, we train our model primarily on Chinese text-video pairs. Therefore, we recommend using Chinese prompt to achieve better results. This repository supports two Text-to-Video models (1.3B and 14B) and two resolutions (480P and 720P). The parameters and configurations for these models are as follows: To facilitate implementation, we will start with a basic version of the inference process that skips the prompt extension step. If you encounter OOM (Out-of-Memory) issues, you can use the `--offloadmodel True` and `--t5cpu` options to reduce GPU memory usage. For example, on an RTX 4090 GPU: > 💡Note: If you are using the `T2V-1.3B` model, we recommend setting the parameter `--sampleguidescale 6`. The `--sampleshift parameter` can be adjusted within the range of 8 to 12 based on the performance. If you want to use `Ulysses` strategy, you should set `--ulyssessize $GPUNUMS`. Note that the `numheads` should be divisible by `ulyssessize` if you wish to use `Ulysess` strategy. For the 1.3B model, the `numheads` is `12` which can't be divided by 8 (as most multi-GPU machines have 8 GPUs). Therefore, it is recommended to use `Ring Strategy` instead. If you want to use `Ring` strategy, you should set `--ringsize $GPUNUMS`. Note that the `sequence length` should be divisible by `ringsize` when using the `Ring` strategy. Of course, you can also combine the use of `Ulysses` and `Ring` strategies. Extending the prompts can effectively enrich the details in the generated videos, further enhancing the video quality. Therefore, we recommend enabling prompt extension. We provide the following two methods for prompt extension: - Use the Dashscope API for extension. - Apply for a `dashscope.apikey` in advance (EN | CN). - Configure the environment variable `DASHAPIKEY` to specify the Dashscope API key. For users of Alibaba Cloud's international site, you also need to set the environment variable `DASHAPIURL` to 'https://dashscope-intl.aliyuncs.com/api/v1'. For more detailed instructions, please refer to the dashscope document. - Use the `qwen-plus` model for text-to-video tasks and `qwen-vl-max` for image-to-video tasks. - You can modify the model used for extension with the parameter `--promptextendmodel`. For example: - By default, the Qwen model on HuggingFace is used for this extension. Users can choose Qwen models or other models based on the available GPU memory size. - For text-to-video tasks, you can use models like `Qwen/Qwen2.5-14B-Instruct`, `Qwen/Qwen2.5-7B-Instruct` and `Qwen/Qwen2.5-3B-Instruct`. - For image-to-video or first-last-frame-to-video tasks, you can use models like `Qwen/Qwen2.5-VL-7B-Instruct` and `Qwen/Qwen2.5-VL-3B-Instruct`. - Larger models generally provide better extension results but require more GPU memory. - You can modify the model used for extension with the parameter `--promptextendmodel` , allowing you to specify either a local model path or a Hugging Face model. For example: You can easily inference Wan2.1-T2V using Diffusers with the following command: > 💡Note: Please note that this example does not integrate Prompt Extension and distributed inference. We will soon update with the integrated prompt extension and multi-GPU version of Diffusers. Similar to Text-to-Video, Image-to-Video is also divided into processes with and without the prompt extension step. The specific parameters and their corresponding settings are as follows: > 💡For the Image-to-Video task, the `size` parameter represents the area of the generated video, with the aspect ratio following that of the original input image. The process of prompt extension can be referenced here. Run with local prompt extension using `Qwen/Qwen2.5-VL-7B-Instruct`: Run with remote prompt extension using `dashscope`: You can easily inference Wan2.1-I2V using Diffusers with the following command: > 💡Note: Please note that this example does not integrate Prompt Extension and distributed inference. We will soon update with the integrated prompt extension and multi-GPU version of Diffusers. First-Last-Frame-to-Video is also divided into processes with and without the prompt extension step. Currently, only 720P is supported. The specific parameters and corresponding settings are as follows: > 💡Similar to Image-to-Video, the `size` parameter represents the area of the generated video, with the aspect ratio following that of the original input image. The process of prompt extension can be referenced here. Run with local prompt extension using `Qwen/Qwen2.5-VL-7B-Instruct`: Run with remote prompt extension using `dashscope`: VACE now supports two models (1.3B and 14B) and two main resolutions (480P and 720P). The input supports any resolution, but to achieve optimal results, the video size should fall within a specific range. The parameters and configurations for these models are as follows: In VACE, users can input text prompt and optional video, mask, and image for video generation or editing. Detailed instructions for using VACE can be found in the User Guide. The execution process is as follows: User-collected materials needs to be preprocessed into VACE-recognizable inputs, including `srcvideo`, `srcmask`, `srcrefimages`, and `prompt`. For R2V (Reference-to-Video Generation), you may skip this preprocessing, but for V2V (Video-to-Video Editing) and MV2V (Masked Video-to-Video Editing) tasks, additional preprocessing is required to obtain video with conditions such as depth, pose or masked regions. For more details, please refer to vacepreproccess. Wan2.1 is a unified model for both image and video generation. Since it was trained on both types of data, it can also generate images. The command for generating images is similar to video generation, as follows: Through manual evaluation, the results generated after prompt extension are superior to those from both closed-source and open-source models. We also conducted extensive manual evaluations to evaluate the performance of the Image-to-Video model, and the results are presented in the table below. The results clearly indicate that Wan2.1 outperforms both closed-source and open-source models. We test the computational efficiency of different Wan2.1 models on different GPUs in the following table. The results are presented in the format: Total time (s) / peak GPU memory (GB). > The parameter settings for the tests presented in this table are as follows: > (1) For the 1.3B model on 8 GPUs, set `--ringsize 8` and `--ulyssessize 1`; > (2) For the 14B model on 1 GPU, use `--offloadmodel True`; > (3) For the 1.3B model on a single 4090 GPU, set `--offloadmodel True --t5cpu`; > (4) For all testings, no prompt extension was applied, meaning `--usepromptextend` was not enabled. > 💡Note: T2V-14B is slower than I2V-14B because the former samples 50 steps while the latter uses 40 steps. Wan2.1 is designed on the mainstream diffusion transformer paradigm, achieving significant advancements in generative capabilities through a series of innovations. These include our novel spatio-temporal variational autoencoder (VAE), scalable training strategies, large-scale data construction, and automated evaluation metrics. Collectively, these contributions enhance the model’s performance and versatility. (1) 3D Variational Autoencoders We propose a novel 3D causal VAE architecture, termed Wan-VAE specifically designed for video generation. By combining multiple strategies, we improve spatio-temporal compression, reduce memory usage, and ensure temporal causality. Wan-VAE demonstrates significant advantages in performance efficiency compared to other open-source VAEs. Furthermore, our Wan-VAE can encode and decode unlimited-length 1080P videos without losing historical temporal information, making it particularly well-suited for video generation tasks. Wan2.1 is designed using the Flow Matching framework within the paradigm of mainstream Diffusion Transformers. Our model's architecture uses the T5 Encoder to encode multilingual text input, with cross-attention in each transformer block embedding the text into the model structure. Additionally, we employ an MLP with a Linear layer and a SiLU layer to process the input time embeddings and predict six modulation parameters individually. This MLP is shared across all transformer blocks, with each block learning a distinct set of biases. Our experimental findings reveal a significant performance improvement with this approach at the same parameter scale. | Model | Dimension | Input Dimension | Output Dimension | Feedforward Dimension | Frequency Dimension | Number of Heads | Number of Layers | |--------|-----------|-----------------|------------------|-----------------------|---------------------|-----------------|------------------| | 1.3B | 1536 | 16 | 16 | 8960 | 256 | 12 | 30 | | 14B | 5120 | 16 | 16 | 13824 | 256 | 40 | 40 | We curated and deduplicated a candidate dataset comprising a vast amount of image and video data. During the data curation process, we designed a four-step data cleaning process, focusing on fundamental dimensions, visual quality and motion quality. Through the robust data processing pipeline, we can easily obtain high-quality, diverse, and large-scale training sets of images and videos. Comparisons to SOTA We compared Wan2.1 with leading open-source and closed-source models to evaluate the performance. Using our carefully designed set of 1,035 internal prompts, we tested across 14 major dimensions and 26 sub-dimensions. We then compute the total score by performing a weighted calculation on the scores of each dimension, utilizing weights derived from human preferences in the matching process. The detailed results are shown in the table below. These results demonstrate our model's superior performance compared to both open-source and closed-source models. Citation If you find our work helpful, please cite us. License Agreement The models in this repository are licensed under the Apache 2.0 License. We claim no rights over the your generated contents, granting you the freedom to use them while ensuring that your usage complies with the provisions of this license. You are fully accountable for your use of the models, which must not involve sharing any content that violates applicable laws, causes harm to individuals or groups, disseminates personal information intended for harm, spreads misinformation, or targets vulnerable populations. For a complete list of restrictions and details regarding your rights, please refer to the full text of the license. We would like to thank the contributors to the SD3, Qwen, umt5-xxl, diffusers and HuggingFace repositories, for their open research. Contact Us If you would like to leave a message to our research or product teams, feel free to join our Discord or WeChat groups!

Wan2.2-I2V-A14B

Wan2.2-T2V-A14B

Wan2.1-VACE-14B-diffusers

NaNK

license:apache-2.0

5,781

Wan2.2-S2V-14B

Wan2.2-S2V-14B: Audio-Driven Cinematic Video Generation This repository features the Wan2.2-S2V-14B model, designed for audio-driven cinematic video generation. It was introduced in the paper: Wan-S2V: Audio-Driven Cinematic Video Generation 💜 Wan Homepage &nbsp&nbsp ｜ &nbsp&nbsp 🖥️ GitHub &nbsp&nbsp | &nbsp&nbsp🤗 Hugging Face Organization &nbsp&nbsp | &nbsp&nbsp🤖 ModelScope Organization &nbsp&nbsp | &nbsp&nbsp 📑 Wan-S2V Paper &nbsp&nbsp | &nbsp&nbsp 📑 Wan2.2 Base Paper &nbsp&nbsp | 🌐 Project Page &nbsp&nbsp | &nbsp&nbsp 📑 Blog &nbsp&nbsp | &nbsp&nbsp 💬 Discord &nbsp&nbsp 📕 使用指南(中文) &nbsp&nbsp | &nbsp&nbsp 📘 User Guide(English) &nbsp&nbsp | &nbsp&nbsp💬 WeChat(微信) &nbsp&nbsp Current state-of-the-art (SOTA) methods for audio-driven character animation demonstrate promising performance for scenarios primarily involving speech and singing. However, they often fall short in more complex film and television productions, which demand sophisticated elements such as nuanced character interactions, realistic body movements, and dynamic camera work. To address this long-standing challenge of achieving film-level character animation, we propose an audio-driven model, which we refere to as Wan-S2V, built upon Wan. Our model achieves significantly enhanced expressiveness and fidelity in cinematic contexts compared to existing approaches. We conducted extensive experiments, benchmarking our method against cutting-edge models such as Hunyuan-Avatar and Omnihuman. The experimental results consistently demonstrate that our approach significantly outperforms these existing solutions. Additionally, we explore the versatility of our method through its applications in long-form video generation and precise video lip-sync editing. Wan: Open and Advanced Large-Scale Video Generative Models We are excited to introduce Wan2.2, a major upgrade to our foundational video models. With Wan2.2, we have focused on incorporating the following innovations: - 👍 Effective MoE Architecture: Wan2.2 introduces a Mixture-of-Experts (MoE) architecture into video diffusion models. By separating the denoising process cross timesteps with specialized powerful expert models, this enlarges the overall model capacity while maintaining the same computational cost. - 👍 Cinematic-level Aesthetics: Wan2.2 incorporates meticulously curated aesthetic data, complete with detailed labels for lighting, composition, contrast, color tone, and more. This allows for more precise and controllable cinematic style generation, facilitating the creation of videos with customizable aesthetic preferences. - 👍 Complex Motion Generation: Compared to Wan2.1, Wan2.2 is trained on a significantly larger data, with +65.6% more images and +83.2% more videos. This expansion notably enhances the model's generalization across multiple dimensions such as motions, semantics, and aesthetics, achieving TOP performance among all open-sourced and closed-sourced models. - 👍 Efficient High-Definition Hybrid TI2V: Wan2.2 open-sources a 5B model built with our advanced Wan2.2-VAE that achieves a compression ratio of 16×16×4. This model supports both text-to-video and image-to-video generation at 720P resolution with 24fps and can also run on consumer-grade graphics cards like 4090. It is one of the fastest 720P@24fps models currently available, capable of serving both the industrial and academic sectors simultaneously. Aug 26, 2025: 🎵 We introduce Wan2.2-S2V-14B, an audio-driven cinematic video generation model, including inference code, model weights, and technical report! Now you can try it on wan.video, ModelScope Gradio or HuggingFace Gradio! Jul 28, 2025: 👋 We have open a HF space using the TI2V-5B model. Enjoy! Jul 28, 2025: 👋 Wan2.2 has been integrated into ComfyUI (CN | EN). Enjoy! Jul 28, 2025: 👋 Wan2.2's T2V, I2V and TI2V have been integrated into Diffusers (T2V-A14B | I2V-A14B | TI2V-5B). Feel free to give it a try! Jul 28, 2025: 👋 We've released the inference code and model weights of Wan2.2. Community Works If your research or project builds upon Wan2.1 or Wan2.2, and you would like more people to see it, please inform us. - DiffSynth-Studio provides comprehensive support for Wan 2.2, including low-GPU-memory layer-by-layer offload, FP8 quantization, sequence parallelism, LoRA training, full training. - Kijai's ComfyUI WanVideoWrapper is an alternative implementation of Wan models for ComfyUI. Thanks to its Wan-only focus, it's on the frontline of getting cutting edge optimizations and hot research features, which are often hard to integrate into ComfyUI quickly due to its more rigid structure. 📑 Todo List - Wan2.2-S2V Speech-to-Video - [x] Inference code of Wan2.2-S2V - [x] Checkpoints of Wan2.2-S2V-14B - [x] ComfyUI integration - [x] Diffusers integration | Models | Download Links | Description | |--------------------|---------------------------------------------------------------------------------------------------------------------------------------------|-------------| | T2V-A14B | 🤗 Huggingface 🤖 ModelScope | Text-to-Video MoE model, supports 480P & 720P | | I2V-A14B | 🤗 Huggingface 🤖 ModelScope | Image-to-Video MoE model, supports 480P & 720P | | TI2V-5B | 🤗 Huggingface 🤖 ModelScope | High-compression VAE, T2V+I2V, supports 720P | | S2V-14B | 🤗 Huggingface 🤖 ModelScope | Speech-to-Video model, supports 480P & 720P | This repository supports the `Wan2.2-S2V-14B` Speech-to-Video model and can simultaneously support video generation at 480P and 720P resolutions. > 💡 This command can run on a GPU with at least 80GB VRAM. - Multi-GPU inference using FSDP + DeepSpeed Ulysses > 💡For the Speech-to-Video task, the `size` parameter represents the area of the generated video, with the aspect ratio following that of the original input image. > 💡The model can generate videos from audio input combined with reference image and optional text prompt. > 💡The `--posevideo` parameter enables pose-driven generation, allowing the model to follow specific pose sequences while generating videos synchronized with audio input. > 💡The `--numclip` parameter controls the number of video clips generated, useful for quick preview with shorter generation time. We test the computational efficiency of different Wan2.2 models on different GPUs in the following table. The results are presented in the format: Total time (s) / peak GPU memory (GB). > The parameter settings for the tests presented in this table are as follows: > (1) Multi-GPU: 14B: `--ulyssessize 4/8 --ditfsdp --t5fsdp`, 5B: `--ulyssessize 4/8 --offloadmodel True --convertmodeldtype --t5cpu`; Single-GPU: 14B: `--offloadmodel True --convertmodeldtype`, 5B: `--offloadmodel True --convertmodeldtype --t5cpu` (--convertmodeldtype converts model parameter types to config.paramdtype); > (2) The distributed testing utilizes the built-in FSDP and Ulysses implementations, with FlashAttention3 deployed on Hopper architecture GPUs; > (3) Tests were run without the `--usepromptextend` flag; > (4) Reported results are the average of multiple samples taken after the warm-up phase. Wan2.2 builds on the foundation of Wan2.1 with notable improvements in generation quality and model capability. This upgrade is driven by a series of key technical innovations, mainly including the Mixture-of-Experts (MoE) architecture, upgraded training data, and high-compression video generation. Wan2.2 introduces Mixture-of-Experts (MoE) architecture into the video generation diffusion model. MoE has been widely validated in large language models as an efficient approach to increase total model parameters while keeping inference cost nearly unchanged. In Wan2.2, the A14B model series adopts a two-expert design tailored to the denoising process of diffusion models: a high-noise expert for the early stages, focusing on overall layout; and a low-noise expert for the later stages, refining video details. Each expert model has about 14B parameters, resulting in a total of 27B parameters but only 14B active parameters per step, keeping inference computation and GPU memory nearly unchanged. The transition point between the two experts is determined by the signal-to-noise ratio (SNR), a metric that decreases monotonically as the denoising step $t$ increases. At the beginning of the denoising process, $t$ is large and the noise level is high, so the SNR is at its minimum, denoted as ${SNR}{min}$. In this stage, the high-noise expert is activated. We define a threshold step ${t}{moe}$ corresponding to half of the ${SNR}{min}$, and switch to the low-noise expert when $t To validate the effectiveness of the MoE architecture, four settings are compared based on their validation loss curves. The baseline Wan2.1 model does not employ the MoE architecture. Among the MoE-based variants, the Wan2.1 & High-Noise Expert reuses the Wan2.1 model as the low-noise expert while uses the Wan2.2's high-noise expert, while the Wan2.1 & Low-Noise Expert uses Wan2.1 as the high-noise expert and employ the Wan2.2's low-noise expert. The Wan2.2 (MoE) (our final version) achieves the lowest validation loss, indicating that its generated video distribution is closest to ground-truth and exhibits superior convergence. (2) Efficient High-Definition Hybrid TI2V To enable more efficient deployment, Wan2.2 also explores a high-compression design. In addition to the 27B MoE models, a 5B dense model, i.e., TI2V-5B, is released. It is supported by a high-compression Wan2.2-VAE, which achieves a $T\times H\times W$ compression ratio of $4\times16\times16$, increasing the overall compression rate to 64 while maintaining high-quality video reconstruction. With an additional patchification layer, the total compression ratio of TI2V-5B reaches $4\times32\times32$. Without specific optimization, TI2V-5B can generate a 5-second 720P video in under 9 minutes on a single consumer-grade GPU, ranking among the fastest 720P@24fps video generation models. This model also natively supports both text-to-video and image-to-video tasks within a single unified framework, covering both academic research and practical applications. Comparisons to SOTAs We compared Wan2.2 with leading closed-source commercial models on our new Wan-Bench 2.0, evaluating performance across multiple crucial dimensions. The results demonstrate that Wan2.2 achieves superior performance compared to these leading models. Citation If you find our work helpful, please cite us. License Agreement The models in this repository are licensed under the Apache 2.0 License. We claim no rights over the your generated contents, granting you the freedom to use them while ensuring that your usage complies with the provisions of this license. You are fully accountable for your use of the models, which must not involve sharing any content that violates applicable laws, causes harm to individuals or groups, disseminates personal information intended for harm, spreads misinformation, or targets vulnerable populations. For a complete list of restrictions and details regarding your rights, please refer to the full text of the license. We would like to thank the contributors to the SD3, Qwen, umt5-xxl, diffusers and HuggingFace repositories, for their open research. Contact Us If you would like to leave a message to our research or product teams, feel free to join our Discord or WeChat groups!

Wan2.1-VACE-1.3B-diffusers

NaNK

license:apache-2.0

4,436

Wan2.2-TI2V-5B

Wan2.1-FLF2V-14B-720P

💜 Wan &nbsp&nbsp ｜ &nbsp&nbsp 🖥️ GitHub &nbsp&nbsp | &nbsp&nbsp🤗 Hugging Face &nbsp&nbsp | &nbsp&nbsp🤖 ModelScope &nbsp&nbsp | &nbsp&nbsp 📑 Technical Report &nbsp&nbsp | &nbsp&nbsp 📑 Blog &nbsp&nbsp | &nbsp&nbsp💬 WeChat Group &nbsp&nbsp | &nbsp&nbsp 📖 Discord &nbsp&nbsp Wan: Open and Advanced Large-Scale Video Generative Models In this repository, we present Wan2.1, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation. Wan2.1 offers these key features: - 👍 SOTA Performance: Wan2.1 consistently outperforms existing open-source models and state-of-the-art commercial solutions across multiple benchmarks. - 👍 Supports Consumer-grade GPUs: The T2V-1.3B model requires only 8.19 GB VRAM, making it compatible with almost all consumer-grade GPUs. It can generate a 5-second 480P video on an RTX 4090 in about 4 minutes (without optimization techniques like quantization). Its performance is even comparable to some closed-source models. - 👍 Multiple Tasks: Wan2.1 excels in Text-to-Video, Image-to-Video, Video Editing, Text-to-Image, and Video-to-Audio, advancing the field of video generation. - 👍 Visual Text Generation: Wan2.1 is the first video model capable of generating both Chinese and English text, featuring robust text generation that enhances its practical applications. - 👍 Powerful Video VAE: Wan-VAE delivers exceptional efficiency and performance, encoding and decoding 1080P videos of any length while preserving temporal information, making it an ideal foundation for video and image generation. Apr 17, 2025: 👋 We introduce Wan2.1 FLF2V with its inference code and weights! Mar 21, 2025: 👋 We are excited to announce the release of the Wan2.1 technical report. We welcome discussions and feedback! Mar 3, 2025: 👋 Wan2.1's T2V and I2V have been integrated into Diffusers (T2V | I2V). Feel free to give it a try! Feb 27, 2025: 👋 Wan2.1 has been integrated into ComfyUI. Enjoy! Feb 25, 2025: 👋 We've released the inference code and weights of Wan2.1. Community Works If your work has improved Wan2.1 and you would like more people to see it, please inform us. - CFG-Zero enhances Wan2.1 (covering both T2V and I2V models) from the perspective of CFG. - TeaCache now supports Wan2.1 acceleration, capable of increasing speed by approximately 2x. Feel free to give it a try! - DiffSynth-Studio provides more support for Wan2.1, including video-to-video, FP8 quantization, VRAM optimization, LoRA training, and more. Please refer to their examples. 📑 Todo List - Wan2.1 Text-to-Video - [x] Multi-GPU Inference code of the 14B and 1.3B models - [x] Checkpoints of the 14B and 1.3B models - [x] Gradio demo - [x] ComfyUI integration - [x] Diffusers integration - [ ] Diffusers + Multi-GPU Inference - Wan2.1 Image-to-Video - [x] Multi-GPU Inference code of the 14B model - [x] Checkpoints of the 14B model - [x] Gradio demo - [x] ComfyUI integration - [x] Diffusers integration - [ ] Diffusers + Multi-GPU Inference - Wan2.1 First-Last-Frame-to-Video - [x] Multi-GPU Inference code of the 14B model - [x] Checkpoints of the 14B model - [x] Gradio demo - [ ] ComfyUI integration - [ ] Diffusers integration - [ ] Diffusers + Multi-GPU Inference | Models | Download Link | Notes | |--------------|-----------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------| | T2V-14B | 🤗 Huggingface 🤖 ModelScope | Supports both 480P and 720P | I2V-14B-720P | 🤗 Huggingface 🤖 ModelScope | Supports 720P | I2V-14B-480P | 🤗 Huggingface 🤖 ModelScope | Supports 480P | T2V-1.3B | 🤗 Huggingface 🤖 ModelScope | Supports 480P | FLF2V-14B | 🤗 Huggingface 🤖 ModelScope | Supports 720P > 💡Note: The 1.3B model is capable of generating videos at 720P resolution. However, due to limited training at this resolution, the results are generally less stable compared to 480P. For optimal performance, we recommend using 480P resolution. For the first-last frame to video generation, we train our model primarily on Chinese text-video pairs. Therefore, we recommend using Chinese prompt to achieve better results. This repository supports two Text-to-Video models (1.3B and 14B) and two resolutions (480P and 720P). The parameters and configurations for these models are as follows: To facilitate implementation, we will start with a basic version of the inference process that skips the prompt extension step. If you encounter OOM (Out-of-Memory) issues, you can use the `--offloadmodel True` and `--t5cpu` options to reduce GPU memory usage. For example, on an RTX 4090 GPU: > 💡Note: If you are using the `T2V-1.3B` model, we recommend setting the parameter `--sampleguidescale 6`. The `--sampleshift parameter` can be adjusted within the range of 8 to 12 based on the performance. If you want to use `Ulysses` strategy, you should set `--ulyssessize $GPUNUMS`. Note that the `numheads` should be divisible by `ulyssessize` if you wish to use `Ulysess` strategy. For the 1.3B model, the `numheads` is `12` which can't be divided by 8 (as most multi-GPU machines have 8 GPUs). Therefore, it is recommended to use `Ring Strategy` instead. If you want to use `Ring` strategy, you should set `--ringsize $GPUNUMS`. Note that the `sequence length` should be divisible by `ringsize` when using the `Ring` strategy. Of course, you can also combine the use of `Ulysses` and `Ring` strategies. Extending the prompts can effectively enrich the details in the generated videos, further enhancing the video quality. Therefore, we recommend enabling prompt extension. We provide the following two methods for prompt extension: - Use the Dashscope API for extension. - Apply for a `dashscope.apikey` in advance (EN | CN). - Configure the environment variable `DASHAPIKEY` to specify the Dashscope API key. For users of Alibaba Cloud's international site, you also need to set the environment variable `DASHAPIURL` to 'https://dashscope-intl.aliyuncs.com/api/v1'. For more detailed instructions, please refer to the dashscope document. - Use the `qwen-plus` model for text-to-video tasks and `qwen-vl-max` for image-to-video tasks. - You can modify the model used for extension with the parameter `--promptextendmodel`. For example: - By default, the Qwen model on HuggingFace is used for this extension. Users can choose Qwen models or other models based on the available GPU memory size. - For text-to-video tasks, you can use models like `Qwen/Qwen2.5-14B-Instruct`, `Qwen/Qwen2.5-7B-Instruct` and `Qwen/Qwen2.5-3B-Instruct`. - For image-to-video or first-last-frame-to-video tasks, you can use models like `Qwen/Qwen2.5-VL-7B-Instruct` and `Qwen/Qwen2.5-VL-3B-Instruct`. - Larger models generally provide better extension results but require more GPU memory. - You can modify the model used for extension with the parameter `--promptextendmodel` , allowing you to specify either a local model path or a Hugging Face model. For example: You can easily inference Wan2.1-T2V using Diffusers with the following command: > 💡Note: Please note that this example does not integrate Prompt Extension and distributed inference. We will soon update with the integrated prompt extension and multi-GPU version of Diffusers. Similar to Text-to-Video, Image-to-Video is also divided into processes with and without the prompt extension step. The specific parameters and their corresponding settings are as follows: > 💡For the Image-to-Video task, the `size` parameter represents the area of the generated video, with the aspect ratio following that of the original input image. The process of prompt extension can be referenced here. Run with local prompt extension using `Qwen/Qwen2.5-VL-7B-Instruct`: Run with remote prompt extension using `dashscope`: You can easily inference Wan2.1-I2V using Diffusers with the following command: > 💡Note: Please note that this example does not integrate Prompt Extension and distributed inference. We will soon update with the integrated prompt extension and multi-GPU version of Diffusers. First-Last-Frame-to-Video is also divided into processes with and without the prompt extension step. Currently, only 720P is supported. The specific parameters and corresponding settings are as follows: > 💡Similar to Image-to-Video, the `size` parameter represents the area of the generated video, with the aspect ratio following that of the original input image. The process of prompt extension can be referenced here. Run with local prompt extension using `Qwen/Qwen2.5-VL-7B-Instruct`: Run with remote prompt extension using `dashscope`: Wan2.1 is a unified model for both image and video generation. Since it was trained on both types of data, it can also generate images. The command for generating images is similar to video generation, as follows: Through manual evaluation, the results generated after prompt extension are superior to those from both closed-source and open-source models. We also conducted extensive manual evaluations to evaluate the performance of the Image-to-Video model, and the results are presented in the table below. The results clearly indicate that Wan2.1 outperforms both closed-source and open-source models. We test the computational efficiency of different Wan2.1 models on different GPUs in the following table. The results are presented in the format: Total time (s) / peak GPU memory (GB). > The parameter settings for the tests presented in this table are as follows: > (1) For the 1.3B model on 8 GPUs, set `--ringsize 8` and `--ulyssessize 1`; > (2) For the 14B model on 1 GPU, use `--offloadmodel True`; > (3) For the 1.3B model on a single 4090 GPU, set `--offloadmodel True --t5cpu`; > (4) For all testings, no prompt extension was applied, meaning `--usepromptextend` was not enabled. > 💡Note: T2V-14B is slower than I2V-14B because the former samples 50 steps while the latter uses 40 steps. Wan2.1 is designed on the mainstream diffusion transformer paradigm, achieving significant advancements in generative capabilities through a series of innovations. These include our novel spatio-temporal variational autoencoder (VAE), scalable training strategies, large-scale data construction, and automated evaluation metrics. Collectively, these contributions enhance the model’s performance and versatility. (1) 3D Variational Autoencoders We propose a novel 3D causal VAE architecture, termed Wan-VAE specifically designed for video generation. By combining multiple strategies, we improve spatio-temporal compression, reduce memory usage, and ensure temporal causality. Wan-VAE demonstrates significant advantages in performance efficiency compared to other open-source VAEs. Furthermore, our Wan-VAE can encode and decode unlimited-length 1080P videos without losing historical temporal information, making it particularly well-suited for video generation tasks. Wan2.1 is designed using the Flow Matching framework within the paradigm of mainstream Diffusion Transformers. Our model's architecture uses the T5 Encoder to encode multilingual text input, with cross-attention in each transformer block embedding the text into the model structure. Additionally, we employ an MLP with a Linear layer and a SiLU layer to process the input time embeddings and predict six modulation parameters individually. This MLP is shared across all transformer blocks, with each block learning a distinct set of biases. Our experimental findings reveal a significant performance improvement with this approach at the same parameter scale. | Model | Dimension | Input Dimension | Output Dimension | Feedforward Dimension | Frequency Dimension | Number of Heads | Number of Layers | |--------|-----------|-----------------|------------------|-----------------------|---------------------|-----------------|------------------| | 1.3B | 1536 | 16 | 16 | 8960 | 256 | 12 | 30 | | 14B | 5120 | 16 | 16 | 13824 | 256 | 40 | 40 | We curated and deduplicated a candidate dataset comprising a vast amount of image and video data. During the data curation process, we designed a four-step data cleaning process, focusing on fundamental dimensions, visual quality and motion quality. Through the robust data processing pipeline, we can easily obtain high-quality, diverse, and large-scale training sets of images and videos. Comparisons to SOTA We compared Wan2.1 with leading open-source and closed-source models to evaluate the performance. Using our carefully designed set of 1,035 internal prompts, we tested across 14 major dimensions and 26 sub-dimensions. We then compute the total score by performing a weighted calculation on the scores of each dimension, utilizing weights derived from human preferences in the matching process. The detailed results are shown in the table below. These results demonstrate our model's superior performance compared to both open-source and closed-source models. Citation If you find our work helpful, please cite us. License Agreement The models in this repository are licensed under the Apache 2.0 License. We claim no rights over the your generated contents, granting you the freedom to use them while ensuring that your usage complies with the provisions of this license. You are fully accountable for your use of the models, which must not involve sharing any content that violates applicable laws, causes harm to individuals or groups, disseminates personal information intended for harm, spreads misinformation, or targets vulnerable populations. For a complete list of restrictions and details regarding your rights, please refer to the full text of the license. We would like to thank the contributors to the SD3, Qwen, umt5-xxl, diffusers and HuggingFace repositories, for their open research. Contact Us If you would like to leave a message to our research or product teams, feel free to join our Discord or WeChat groups!